Yuval Aboulafia
3bf5591efe
fix F541 f-string without any placeholders
3 years ago
linuxmobile ( リナックス )
5a650055de
Removed lenght in sd_model at line 115
...
Commit eba60a4 is what is causing this error, delete the length check in sd_model starting at line 115 and it's fine.
https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/5971#issuecomment-1364507379
3 years ago
AUTOMATIC1111
eba60a42eb
Merge pull request #5627 from deanpress/patch-1
...
fix: fallback model_checkpoint if it's empty
3 years ago
MrCheeze
ec0a48826f
unconditionally set use_ema=False if value not specified (True never worked, and all configs except v1-inpainting-inference.yaml already correctly set it to False)
3 years ago
Dean van Dugteren
59c6511494
fix: fallback model_checkpoint if it's empty
...
This fixes the following error when SD attempts to start with a deleted checkpoint:
```
Traceback (most recent call last):
File "D:\Web\stable-diffusion-webui\launch.py", line 295, in <module>
start()
File "D:\Web\stable-diffusion-webui\launch.py", line 290, in start
webui.webui()
File "D:\Web\stable-diffusion-webui\webui.py", line 132, in webui
initialize()
File "D:\Web\stable-diffusion-webui\webui.py", line 62, in initialize
modules.sd_models.load_model()
File "D:\Web\stable-diffusion-webui\modules\sd_models.py", line 283, in load_model
checkpoint_info = checkpoint_info or select_checkpoint()
File "D:\Web\stable-diffusion-webui\modules\sd_models.py", line 117, in select_checkpoint
checkpoint_info = checkpoints_list.get(model_checkpoint, None)
TypeError: unhashable type: 'list'
```
3 years ago
MrCheeze
bd81a09eac
fix support for 2.0 inpainting model while maintaining support for 1.5 inpainting model
3 years ago
AUTOMATIC1111
ec5e072124
Merge pull request #4841 from R-N/vae-fix-none
...
Fix None option of VAE selector
3 years ago
Jay Smith
1ed4f0e228
Depth2img model support
3 years ago
AUTOMATIC
0376da180c
make it possible to save nai model using safetensors
3 years ago
AUTOMATIC
dac9b6f15d
add safetensors support for model merging #4869
3 years ago
AUTOMATIC
6074175faa
add safetensors to requirements
3 years ago
AUTOMATIC1111
f108782e30
Merge pull request #4930 from Narsil/allow_to_load_safetensors_file
...
Supporting `*.safetensors` format.
3 years ago
MrCheeze
1e506657e1
no-half support for SD 2.0
3 years ago
Nicolas Patry
0efffbb407
Supporting `*.safetensors` format.
...
If a model file exists with extension `.safetensors` then we can load it
more safely than with PyTorch weights.
3 years ago
Muhammad Rizqi Nur
8662b5e57f
Merge branch 'a1111' into vae-fix-none
3 years ago
Muhammad Rizqi Nur
2c5ca706a7
Remove no longer necessary parts and add vae_file safeguard
3 years ago
Muhammad Rizqi Nur
c7be83bf02
Misc
...
Misc
3 years ago
Muhammad Rizqi Nur
abc1e79a5d
Fix base VAE caching was done after loading VAE, also add safeguard
3 years ago
cluder
eebf49592a
restore #4035 behavior
...
- if checkpoint cache is set to 1, keep 2 models in cache (current +1 more)
3 years ago
cluder
3b51d239ac
- do not use ckpt cache, if disabled
...
- cache model after is has been loaded from file
3 years ago
AUTOMATIC
99043f3360
fix one of previous merges breaking the program
3 years ago
AUTOMATIC1111
24fc05cf57
Merge branch 'master' into fix-ckpt-cache
3 years ago
digburn
3780ad3ad8
fix: loading models without vae from cache
3 years ago
Muhammad Rizqi Nur
fb3b564801
Merge branch 'master' into fix-ckpt-cache
3 years ago
AUTOMATIC
f2a5cbe6f5
fix #3986 breaking --no-half-vae
3 years ago
Muhammad Rizqi Nur
056f06d373
Reload VAE without reloading sd checkpoint
3 years ago
Muhammad Rizqi Nur
f8c6468d42
Merge branch 'master' into vae-picker
3 years ago
Jairo Correa
af758e97fa
Unload sd_model before loading the other
3 years ago
Muhammad Rizqi Nur
bf7a699845
Fix #4035 for real now
3 years ago
Muhammad Rizqi Nur
36966e3200
Fix #4035
3 years ago
Muhammad Rizqi Nur
726769da35
Checkpoint cache by combination key of checkpoint and vae
3 years ago
Muhammad Rizqi Nur
cb31abcf58
Settings to select VAE
3 years ago
AUTOMATIC1111
9553a7e071
Merge pull request #3818 from jwatzman/master
...
Reduce peak memory usage when changing models
3 years ago
Antonio
5d5dc64064
Natural sorting for dropdown checkpoint list
...
Example:
Before After
11.ckpt 11.ckpt
ab.ckpt ab.ckpt
ade_pablo_step_1000.ckpt ade_pablo_step_500.ckpt
ade_pablo_step_500.ckpt ade_pablo_step_1000.ckpt
ade_step_1000.ckpt ade_step_500.ckpt
ade_step_1500.ckpt ade_step_1000.ckpt
ade_step_2000.ckpt ade_step_1500.ckpt
ade_step_2500.ckpt ade_step_2000.ckpt
ade_step_3000.ckpt ade_step_2500.ckpt
ade_step_500.ckpt ade_step_3000.ckpt
atp_step_5500.ckpt atp_step_5500.ckpt
model1.ckpt model1.ckpt
model10.ckpt model10.ckpt
model1000.ckpt model33.ckpt
model33.ckpt model50.ckpt
model400.ckpt model400.ckpt
model50.ckpt model1000.ckpt
moo44.ckpt moo44.ckpt
v1-4-pruned-emaonly.ckpt v1-4-pruned-emaonly.ckpt
v1-5-pruned-emaonly.ckpt v1-5-pruned-emaonly.ckpt
v1-5-pruned.ckpt v1-5-pruned.ckpt
v1-5-vae.ckpt v1-5-vae.ckpt
3 years ago
Josh Watzman
b50ff4f4e4
Reduce peak memory usage when changing models
...
A few tweaks to reduce peak memory usage, the biggest being that if we
aren't using the checkpoint cache, we shouldn't duplicate the model
state dict just to immediately throw it away.
On my machine with 16GB of RAM, this change means I can typically change
models, whereas before it would typically OOM.
3 years ago
AUTOMATIC
321bacc6a9
call model_loaded_callback after setting shared.sd_model in case scripts refer to it using that
3 years ago
MrCheeze
0df94d3fcf
fix aesthetic gradients doing nothing after loading a different model
3 years ago
AUTOMATIC
2b91251637
removed aesthetic gradients as built-in
...
added support for extensions
3 years ago
AUTOMATIC
ac0aa2b18e
loading SD VAE, see PR #3303
3 years ago
AUTOMATIC
df57064093
do not load aesthetic clip model until it's needed
...
add refresh button for aesthetic embeddings
add aesthetic params to images' infotext
3 years ago
AUTOMATIC
7d6b388d71
Merge branch 'ae'
3 years ago
random_thoughtss
49533eed9e
XY grid correctly re-assignes model when config changes
3 years ago
random_thoughtss
708c3a7bd8
Added PLMS hijack and made sure to always replace methods
3 years ago
random_thoughtss
8e7097d06a
Added support for RunwayML inpainting model
3 years ago
AUTOMATIC
f894dd552f
fix for broken checkpoint merger
3 years ago
MalumaDev
2362d5f00e
Merge branch 'master' into test_resolve_conflicts
3 years ago
AUTOMATIC
10aca1ca3e
more careful loading of model weights (eliminates some issues with checkpoints that have weird cond_stage_model layer names)
3 years ago
MalumaDev
9324cdaa31
ui fix, re organization of the code
3 years ago
AUTOMATIC1111
af144ebdc7
Merge branch 'master' into ckpt-cache
3 years ago
Rae Fu
e21f01f645
add checkpoint cache option to UI for faster model switching
...
switching time reduced from ~1500ms to ~280ms
3 years ago